© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 3029
    Prev
    Next
    INDEX
    Explanations

    doing yourself

    np_acts-logits-general · gemini-2.5-flash-lite

    self producing actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     slou
    0.49
    ли
    0.45
    鶴
    0.44
     של
    0.43
    केश
    0.43
     त्वरित
    0.43
    居家
    0.43
    衣
    0.43
    шую
    0.42
    긴
    0.42
    POSITIVE LOGITS
    Wit
    0.41
     OZ
    0.40
     asks
    0.40
     nombreuses
    0.40
     peur
    0.40
     lɛ
    0.40
     offline
    0.39
     solche
    0.38
     via
    0.38
    എം
    0.38
    Activations Density 0.001%

    No Known Activations